Skip to main content

No project description provided

Project description

Unifying and Aligning Multifacted AI Explanations

Code Structure

  • /src: Contains the TypeScript code used to generate the visualizations.
  • /pyWidget contains the python code that create ML models, generate explanations, and call the visualization code.

Depedencies

  • run npm install to install the dependencies for typescript

  • conda env create -f environment.yaml to install the dependencies for python

How to Run

Dev Mode

  1. Execute npm run widgetDev. The compiled TypeScript code will be stored in the /bundle directory. The hot module replacement will re-bundle the outputs when there is a change in src.
  2. Activate the conda environment using conda activate mixai.
  3. Launch the notebook pyWidget/explanation.ipynb. The Python code within will invoke the bundled TypeScript code to produce visualizations.

Product Mode

[place holder]

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

multixai-1.0.0.tar.gz (937.7 kB view details)

Uploaded Source

Built Distribution

multixai-1.0.0-py2.py3-none-any.whl (917.2 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file multixai-1.0.0.tar.gz.

File metadata

  • Download URL: multixai-1.0.0.tar.gz
  • Upload date:
  • Size: 937.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.5

File hashes

Hashes for multixai-1.0.0.tar.gz
Algorithm Hash digest
SHA256 cc086bf56a2c252762d452ca3765d15692d27bbdbb01ff4ed637339a0c7e2a58
MD5 79697265f35b32b23b562e6d99191b62
BLAKE2b-256 60a7d6fe9fe68f4998577943e42a65e0646982d820e6bdf3c91d3990798b67b1

See more details on using hashes here.

File details

Details for the file multixai-1.0.0-py2.py3-none-any.whl.

File metadata

  • Download URL: multixai-1.0.0-py2.py3-none-any.whl
  • Upload date:
  • Size: 917.2 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.5

File hashes

Hashes for multixai-1.0.0-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 07bb6b8613b7c66df9ebeeec7024a1a54aac66edeeb0b033c9f0a1ef3d421b9f
MD5 e0f9e9ff3fb84ac8454cd22872b81e1c
BLAKE2b-256 1fbc890849414dd2439f15a96a5729013f4f3b2d7b8a0d2da8391e531268a377

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page